Evaluation of classification approaches for distinguishing brain states predictive of episodic memory performance from electroencephalography: Abbreviated Title: Evaluating methods of classifying memory states from EEG.

Previous studies have attempted to separate single trial neural responses for events a person is likely to remember from those they are likely to forget using machine learning classification methods. Successful single trial classification holds potential for translation into the clinical realm for real-time detection of memory and other cognitive states to provide real-time interventions (i.e., brain-computer interfaces). However, most of these studies-and classification analyses in general- do not make clear if the chosen methodology is optimally suited for the classification of memory-related brain states. To address this problem, we systematically compared different methods for every step of classification (i.e., feature extraction, feature selection, classifier selection) to investigate which methods work best for decoding episodic memory brain states-the first analysis of its kind. Using an adult lifespan sample EEG dataset collected during performance of an episodic context encoding and retrieval task, we found that no specific feature type (including Common Spatial Pattern (CSP)-based features, mean, variance, correlation, features based on AR model, entropy, phase, and phase synchronization) outperformed others consistently in distinguishing different memory classes. However, extracting all of these feature types consistently outperformed extracting only one type of feature. Additionally, the combination of filtering and sequential forward selection was the optimal method to select the effective features compared to filtering alone or performing no feature selection at all. Moreover, although all classifiers performed at a fairly similar level, LASSO was consistently the highest performing classifier compared to other commonly used options (i.e., naïve Bayes, SVM, and logistic regression) while naïve Bayes was the fastest classifier. Lastly, for multiclass classification (i.e., levels of context memory confidence and context feature perception), generalizing the binary classification using the binary decision tree performed better than the voting or one versus rest method. These methods were shown to outperform alternative approaches for three orthogonal datasets (i.e., EEG working memory, EEG motor imagery, and MEG working memory), supporting their generalizability. Our results provide an optimized methodological process for classifying single-trial neural data and provide important insight and recommendations for a cognitive neuroscientist's ability to make informed choices at all stages of the classification process for predicting memory and other cognitive states.

Context Memory Encoding and Retrieval Temporal Dynamics are Modulated by Attention across the Adult Lifespan.

Episodic memories are multidimensional, including simple and complex features. How we successful encode and recover these features in time, whether these temporal dynamics are preserved across age, even under conditions of reduced memory performance, and the role of attention on these temporal dynamics is unknown. In the current study, we applied time-resolved multivariate decoding to oscillatory electroencephalography (EEG) in an adult lifespan sample to investigate the temporal order of successful encoding and recognition of simple and complex perceptual context features. At encoding, participants studied pictures of black and white objects presented with both color (low-level/simple) and scene (high-level/complex) context features and subsequently made context memory decisions for both features. Attentional demands were manipulated by having participants attend to the relationship between the object and either the color or scene while ignoring the other context feature. Consistent with hierarchical visual perception models, simple visual features (color) were successfully encoded earlier than were complex features (scenes). These features were successfully recognized in the reverse temporal order. Importantly, these temporal dynamics were both dependent on whether these context features were in the focus of one's attention, and preserved across age, despite age-related context memory impairments. These novel results support the idea that episodic memories are encoded and retrieved successively, likely dependent on the input and output pathways of the medial temporal lobe (MTL), and attentional influences that bias activity within these pathways across age.

Retrospective Attention in Short-Term Memory Has a Lasting Effect on Long-Term Memory Across Age.

OBJECTIVES: Declines in both short- and long-term memory are typical of healthy aging. Recent findings suggest that retrodictive attentional cues ("retro-cues") that indicate the location of to-be-probed items in short-term memory (STM) have a lasting impact on long-term memory (LTM) performance in young adults. Whether older adults can also use retro-cues to facilitate both STM and LTM is unknown. METHOD: Young and older adults performed a visual STM task in which spatially informative retro-cues or noninformative neutral-cues were presented during STM maintenance of real-world objects. We tested participants' memory at both STM and LTM delays for objects that were previously cued with retrodictive or neutral-cues during STM order to measure the lasting impact of retrospective attention on LTM. RESULTS: Older adults showed reduced STM and LTM capacity compared to young adults. However, they showed similar magnitude retro-cue memory benefits as young adults at both STM and LTM delays. DISCUSSION: To the best of our knowledge, this is the first study to investigate whether retro-cues in STM facilitate the encoding of objects into LTM such that they are more likely to be subsequently retrieved by older adults. Our results support the idea that retrospective attention can be an effective means by which older adults can improve their STM and LTM performance, even in the context of reduced memory capacity.

Decoding selective attention to context memory: An aging study.

Emerging evidence has suggested that the tendency for older adults to bind too much contextual information during encoding (i.e., hyper-binding) may contribute to poorer memory for relevant contextual information during retrieval. While these findings are consistent with theories of age-related declines in selective attention and inhibitory control, the degree to which older adults are able to selectively attend to relevant contextual information during encoding is unknown. To better understand the neural dynamics associated with selective attention during encoding, the current study applied multivariate pattern analyses (MVPA) to oscillatory EEG in order to track moment-to-moment shifts of attention between relevant and irrelevant contextual information during encoding. Young and older adults studied pictures of objects in the presence of two contextual features: a color and a scene, and their attention was directed to the object's relationship with one of those contexts (i.e., target context). Results showed that patterns of oscillatory power successfully predicted whether selective attention was directed to a scene or color, across age groups. Individual differences in overall classification performance were associated with individual differences in target context memory accuracy during retrieval. However, changes in classification performance within a trial, suggestive of fluctuations in selective attention, predicted individual differences in hyper-binding. To the best of our knowledge, this is the first study to use MPVA techniques to decode attention during episodic encoding and the impact of attentional shifts toward distracting information on age-related context memory impairments and hyper-binding. These results are consistent with the as-of-yet unsubstantiated theory that age-related declines in context memory may be attributable to poorer selective attention and/or greater inhibitory deficits in older adults.

Age-related changes in neural oscillations supporting context memory retrieval.

Recent evidence suggests that directing attention toward single item-context associations during encoding improves young and older adults' context memory performance and reduces demands on executive functions during retrieval. In everyday situations, there are many event features competing for our attention, and our ability to successfully recover those details may depend on our ability to ignore others. Failures of selective attention may contribute to older adults' context memory impairments. In the current electroencephalogram (EEG) study, we assessed the effects of age on processes supporting successful context memory retrieval of selectively attended features as indexed by neural oscillations. During encoding, young and older adults were directed to attend to a picture of an object and its relationship to one of two concurrently presented contextual details: a color or scene. At retrieval, we tested their memory for the object, its attended and unattended context features, and their confidence for both the attended and unattended features. Both groups showed greater memory for attended than unattended contextual features. However, older adults showed evidence of hyper-binding between attended and unattended context features while the young adults did not. EEG results in the theta band suggest that young and older adults recollect similar amounts of information but brain-behavior correlations suggest that this information was supportive of contextual memory performance, particularly for young adults. By contrast, sustained beta desynchronization, indicative of sensory reactivation and episodic reconstruction, was correlated with contextual memory performance for older adults only. We conclude that older adults' inhibition deficits during encoding reduced the selectivity of their contextual memories, which led to reliance on executive functions like episodic reconstruction to support successful memory retrieval.

The lasting memory enhancements of retrospective attention.

Behavioral research has shown that spatial cues that orient attention toward task relevant items being maintained in visual short-term memory (VSTM) enhance item memory accuracy. However, it is unknown if these retrospective attentional cues ("retro-cues") enhance memory beyond typical short-term memory delays. It is also unknown whether retro-cues affect the spatial information associated with VSTM representations. Emerging evidence suggests that processes that affect short-term memory maintenance may also affect long-term memory (LTM) but little work has investigated the role of attention in LTM. In the current event-related potential (ERP) study, we investigated the duration of retrospective attention effects and the impact of retrospective attention manipulations on VSTM representations. Results revealed that retro-cueing improved both VSTM and LTM memory accuracy and that posterior maximal ERPs observed during VSTM maintenance predicted subsequent LTM performance. N2pc ERPs associated with attentional selection were attenuated by retro-cueing suggesting that retrospective attention may disrupt maintenance of spatial configural information in VSTM. Collectively, these findings suggest that retrospective attention can alter the structure of memory representations, which impacts memory performance beyond short-term memory delays.

Age-related deficits in selective attention during encoding increase demands on episodic reconstruction during context retrieval: An ERP study.

Previous event-related potential (ERP) and neuroimaging evidence suggests that directing attention toward single item-context associations compared to intra-item features at encoding improves context memory performance and reduces demands on strategic retrieval operations in young and older adults. In everyday situations, however, there are multiple event features competing for our attention. It is not currently known how selectively attending to one contextual feature while attempting to ignore another influences context memory performance and the processes that support successful retrieval in the young and old. We investigated this issue in the current ERP study. Young and older participants studied pictures of objects in the presence of two contextual features: a color and a scene, and their attention was directed to the object's relationship with one of those contexts. Participants made context memory decisions for both attended and unattended contexts and rated their confidence in those decisions. Behavioral results showed that while both groups were generally successful in applying selective attention during context encoding, older adults were less confident in their context memory decisions for attended features and showed greater dependence in context memory accuracy for attended and unattended contextual features (i.e., hyper-binding). ERP results were largely consistent between age groups but older adults showed a more pronounced late posterior negativity (LPN) implicated in episodic reconstruction processes. We conclude that age-related suppression deficits during encoding result in reduced selectivity in context memory, thereby increasing subsequent demands on episodic reconstruction processes when sought after details are not readily retrieved.